Autonomous Drone Navigation Using Reinforcement Learning and SLAM

This research project investigates autonomous drone navigation in GPS-denied indoor environments by combining a Simultaneous Localization and Mapping (SLAM) pipeline for real-time environment mapping with a reinforcement-learning policy for obstacle-avoiding path selection toward a target waypoint.

A simulated drone (in a physics-based simulator) uses visual/LiDAR SLAM to build an occupancy map on the fly, while a deep reinforcement learning agent (trained with Proximal Policy Optimization) learns to select local velocity commands that balance progress toward the goal against proximity to mapped obstacles.

The study evaluates navigation success rate, path efficiency versus a classical A*-on-occupancy-map baseline, and robustness to sensor noise, and discusses the sim-to-real gap challenges that would need to be addressed before deploying the trained policy on physical drone hardware.

Detailed Project Description

Autonomous Drone Navigation Using Reinforcement Learning and SLAM demonstrates closed-loop motion control: sensor input is turned into motor commands so the machine moves precisely and safely.

How It Works
1. Motors/servos are driven through a driver board from the controller's PWM outputs.
2. Commands come from a remote (Wi-Fi/BLE/RF/gesture) or from an autonomous algorithm.
3. Sensors (IMU, encoders, distance, GPS, LiDAR) provide feedback for stabilisation and obstacle avoidance.
4. A control loop adjusts motor outputs several times per second.

Key Components and Their Role
- GPS module (NEO-6M): receiver that provides latitude, longitude, speed and time over UART/NMEA.
- LiDAR: laser range sensor used to map the surroundings.

Implementation Steps
1. Collect the components and study each module's datasheet (pin-out, voltage, interface).
2. Wire the circuit on a breadboard following the pin mapping; power sensors from the correct rail (3.3 V / 5 V).
3. Install ROS, Gazebo / AirSim, Python (Stable-Baselines3) and the required libraries; flash a minimal test sketch for each module separately.
4. Write the main firmware: read sensors → process → drive outputs / send data.
5. Configure network or cloud credentials and test communication end-to-end.
6. Calibrate thresholds, add error handling (reconnect, sensor time-out) and run a long-duration test.
7. Finalise on a PCB / enclosure and document wiring, code and results.

Key Features
- Remote or autonomous control
- Sensor feedback
- Obstacle handling
- Adjustable speed / precision

Expected Output
On completion the student will have a machine that follows the commanded path or task reliably, with telemetry visible to the operator.

Deliverables
- Complete source code with comments
- Circuit diagram and pin mapping
- Project report with screenshots and results
- Demonstration-ready build